compute_restart_instance · Google Cloud MCP: Risk & Policy

WHAT IT DOES

What compute_restart_instance does on Google Cloud

AI agents invoke compute_restart_instance to trigger actions in Google Cloud. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why compute_restart_instance needs a policy

This tool executes an action on cloud infrastructure with real-world consequences. While not destructive (data is not deleted/overwritten) or financial, restarting an instance is an Execute action because it runs an operation external to the MCP server that could disrupt services, cause downtime, or trigger cascading failures depending on the instance's role.

From the tool's definition Tool name 'compute_restart_instance' and description 'Restart a Compute Engine instance' indicate the tool triggers an external operation (restarting a VM instance) whose effects depend on which instance is targeted.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

compute_restart_instance Rate-limited

compute_restart_instance stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "compute_restart_instance": {
      "limits": [
        {
          "counter": "compute_restart_instance_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Google Cloud, so you can run agents against it safely.

FAQ

Questions about compute_restart_instance

What does the compute_restart_instance tool do? +

Restart a Compute Engine instance. It is categorised as a Execute tool in the Google Cloud MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on compute_restart_instance? +

Register the Google Cloud MCP server in PolicyLayer and add a rule for compute_restart_instance: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Google Cloud. Nothing to install.

What risk level is compute_restart_instance? +

compute_restart_instance is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit compute_restart_instance? +

Yes. Add a rate_limit block to the compute_restart_instance rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block compute_restart_instance completely? +

Set action: deny in the PolicyLayer policy for compute_restart_instance. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides compute_restart_instance? +

compute_restart_instance is provided by the Google Cloud MCP server (lockon-n/google-cloud-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.